• Journal of Convergence for Information Technology
• /
• v.12 no.1
• /
• pp.31-38
• /
• 2022

This paper applies an expert independent unsupervised neural network learning-based multivariate time series data analysis model, MSCRED(Multi-Scale Convolutional Recurrent Encoder-Decoder), and to overcome the limitation, because the MCRED is based on Auto-encoder model, that train data must not to be contaminated, by using learning data sampling technique, called Subset Sampling Validation. By using the vibration data of power plant equipment that has been labeled, the classification performance of MSCRED is evaluated with the Anomaly Score in many cases, 1) the abnormal data is mixed with the training data 2) when the abnormal data is removed from the training data in case 1. Through this, this paper presents an expert-independent anomaly diagnosis framework that is strong against error data, and presents a concise and accurate solution in various fields of multivariate time series data.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.11-18
• /
• 2022

De novo drug design is the process of developing new drugs that can interact with biological targets such as protein receptors. Traditional process of de novo drug design consists of drug candidate discovery and drug development, but it requires a long time of more than 10 years to develop a new drug. Deep learning-based methods are being studied to shorten this period and efficiently find chemical compounds for new drug candidates. Many existing deep learning-based drug design models utilize recurrent neural networks to generate a chemical entity represented by SMILES strings, but due to the disadvantages of the recurrent networks, such as slow training speed and poor understanding of complex molecular formula rules, there is room for improvement. To overcome these shortcomings, we propose a deep learning model for SMILES string generation using variational autoencoders with self-attention mechanism. Our proposed model decreased the training time by 1/26 compared to the latest drug design model, as well as generated valid SMILES more effectively.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.177-189
• /
• 2023

Malware detection is an increasingly important operational focus in cyber security, particularly given the fast pace of such threats (e.g., new malware variants introduced every day). There has been great interest in exploring the use of machine learning techniques in automating and enhancing the effectiveness of malware detection and analysis. In this paper, we present a deep recurrent neural network solution as a stacked Long Short-Term Memory (LSTM) with a pre-training as a regularization method to avoid random network initialization. In our proposal, we use global and short dependencies of the inputs. With pre-training, we avoid random initialization and are able to improve the accuracy and robustness of malware threat hunting. The proposed method speeds up the convergence (in comparison to stacked LSTM) by reducing the length of malware OpCode or bytecode sequences. Hence, the complexity of our final method is reduced. This leads to better accuracy, higher Mattews Correlation Coefficients (MCC), and Area Under the Curve (AUC) in comparison to a standard LSTM with similar detection time. Our proposed method can be applied in real-time malware threat hunting, particularly for safety critical systems such as eHealth or Internet of Military of Things where poor convergence of the model could lead to catastrophic consequences. We evaluate the effectiveness of our proposed method on Windows, Ransomware, Internet of Things (IoT), and Android malware datasets using both static and dynamic analysis. For the IoT malware detection, we also present a comparative summary of the performance on an IoT-specific dataset of our proposed method and the standard stacked LSTM method. More specifically, of our proposed method achieves an accuracy of 99.1% in detecting IoT malware samples, with AUC of 0.985, and MCC of 0.95; thus, outperforming standard LSTM based methods in these key metrics.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.13 no.1
• /
• pp.7-14
• /
• 2006

A breeding programme was initiated during 2001 to introduce sex-limited larval markings to a productive multivoltine breed - BL67 from an inbred sex-limited line, MY1 (SL) maintained at Central Sericultural Research and Training Institute, Mysore. Introgressive hybridization, recurrent backcrossing for six generations followed by sib-mating resulted in synthesis of a new multivoltine silkworm breed BL67 (SL) with sex-limited larval markings. The new breed was studied for combining ability by crossing with eight bivoltine breeds viz., $NB_4D_2,\;CSR_2,\;CSR_2 (SL),\;CSR_2,\;CSR_4,\;CSR_8,\;CSR_{18}\;and\;CSR_{19}$. General combining ability effects of the new breed showed its superiority over the popular Pure Mysore by expressing significant GCA effects for six out of twelve characters whereas the results are on par with the original multivoltine breed. The hybrid $BL67(SL){\times}CSR2(SL)$ excelled in several quantitative characters such as pupation rate (90.2%), cocoon weight (1.97 g), cocoon shell weight (40 cg), cocoon shell ratio (20.3%), filament length (918 m), denier (2.96), raw silk percentage (14.96%) and neatness (90 p). Studies on cocoon size variability revealed that the cocoons of $BL67(SL){\times}CSR2(SL)$ were found comparatively uniform showing less standard deviation of 6.55 and co-efficient of variation of 3.91 %. The suitability of newly developed breed for easy grain age operation and commercial exploitation with promising hybrid have been discussed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.535-538
• /
• 2001

Since 1990s, many literatures have shown that connectionist models, such as back propagation, recurrent network, and RBF (Radial Basis Function) outperform the traditional models, MA (Moving Average), AR (Auto Regressive), and ARIMA (Auto Regressive Integrated Moving Average) in time series prediction. Neural based approaches to time series prediction require the enough length of historical measurements to generate the enough number of training patterns. The more training patterns, the better the generalization of MLP is. The researches about the schemes of generating artificial training patterns and adding to the original ones have been progressed and gave me the motivation of developing VTG schemes in 1996. Virtual term is an estimated measurement, X(t+0.5) between X(t) and X(t+1), while the given measurements in the series are called actual terms. VTG (Virtual Tern Generation) is the process of estimating of X(t+0.5), and VTG schemes are the techniques for the estimation of virtual terms. In this paper, the alternative VTG schemes to the VTG schemes proposed in 1996 will be proposed and applied to multivariate time series prediction. The VTG schemes proposed in 1996 are called deterministic VTG schemes, while the alternative ones are called stochastic VTG schemes in this paper.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.479-487
• /
• 2021

In this paper, we propose an Sound Event Detection (SED) model using self-training based on a noisy student model. The proposed SED model consists of two stages. In the first stage, a mean-teacher model based on an Residual Convolutional Recurrent Neural Network (RCRNN) is constructed to provide target labels regarding weakly labeled or unlabeled data. In the second stage, a self-training-based noisy student model is constructed by applying different noise types. That is, feature noises, such as time-frequency shift, mixup, SpecAugment, and dropout-based model noise are used here. In addition, a semi-supervised loss function is applied to train the noisy student model, which acts as label noise injection. The performance of the proposed SED model is evaluated on the validation set of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2020 Challenge Task 4. The experiments show that the single model and ensemble model of the proposed SED based on the noisy student model improve F1-score by 4.6 % and 3.4 % compared to the top-ranked model in DCASE 2020 challenge Task 4, respectively.

• The Journal of Korea Robotics Society
• /
• v.13 no.1
• /
• pp.16-25
• /
• 2018

The talking head (TH) indicates an utterance face animation generated based on text and voice input. In this paper, we propose the generation method of TH with facial expression and intonation by speech input only. The problem of generating TH from speech can be regarded as a regression problem from the acoustic feature sequence to the facial code sequence which is a low dimensional vector representation that can efficiently encode and decode a face image. This regression was modeled by bidirectional RNN and trained by using SAVEE database of the front utterance face animation database as training data. The proposed method is able to generate TH with facial expression and intonation TH by using acoustic features such as MFCC, dynamic elements of MFCC, energy, and F0. According to the experiments, the configuration of the BLSTM layer of the first and second layers of bidirectional RNN was able to predict the face code best. For the evaluation, a questionnaire survey was conducted for 62 persons who watched TH animations, generated by the proposed method and the previous method. As a result, 77% of the respondents answered that the proposed method generated TH, which matches well with the speech.

• Clinics in Shoulder and Elbow
• /
• v.19 no.2
• /
• pp.110-116
• /
• 2016

Background: Arthroscopic surgical repair is a better intervention than non-operative (conservative) treatment for patients with shoulder dislocations. This systematic review determined the numbers-needed-to-treat (NNT) and relative risk reduction (RRR) associated with arthroscopic surgical repair versus non-operative treatment in reducing recurrence rates among patients with first-time traumatic anterior shoulder dislocations. Methods: We searched Google Scholar, MEDLINE, SPORTDiscus, and CINAHL from inception in 2015. All articles had to compare arthroscopic surgical repair and non-operative treatment and be written in English. We used the total number of subjects and the number of recurrent dislocations within each treatment to calculate the NNT and RRR for each study and the pooled data. Results: Six articles were selected and all clearly demonstrated that the arthroscopic surgical repair was more effective than non-operative treatment in reducing the recurrence episodes. The pooled NNT was 1.76 (95% confidence interval [CI]=NNT to benefit 1.50-2.13) and the pooled RRR was 86.0% (95% CI=77.0%-92.0%) among individuals who underwent arthroscopic repair. The average follow-up time was 56 months. Conclusions: A Strength of Recommendation Taxonomy level of evidence of 1 with a grade A recommendation supports the use of arthroscopic surgical repair over non-operative treatment in prevention of first-time traumatic anterior shoulder dislocations. We suggest that sports medicine practitioners consider the patients' age, occupation, and physical activity level when making a clinical decision.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.2
• /
• pp.486-503
• /
• 2023

Logs play an important role in mastering the health of the system, experienced operation and maintenance engineer can judge which part of the system has a problem by checking the logs. In recent years, many system architectures have changed from single application to distributed application, which leads to a very huge number of logs in the system and manually check the logs to find system errors impractically. To solve the above problems, we propose a method based on Message Middleware and ATT-GRU (Attention Gate Recurrent Unit) to detect the logs anomaly of distributed systems. The works of this paper mainly include two aspects: (1) We design a high-performance distributed logs collection architecture to complete the logs collection of the distributed system. (2)We improve the existing GRU by introducing the attention mechanism to weight the key parts of the logs sequence, which can improve the training efficiency and recognition accuracy of the model to a certain extent. The results of experiments show that our method has better superiority and reliability.

• Journal of Ocean Engineering and Technology
• /
• v.38 no.1
• /
• pp.18-29
• /
• 2024

Waves are a complex phenomenon in marine and coastal areas, and accurate wave prediction is essential for the safety and resource management of ships at sea. In this study, three types of machine learning techniques specialized in nonlinear data processing were used to predict the waves of Korea waters. An optimized algorithm for each area is presented for performance evaluation and comparison. The optimal parameters were determined by varying the window size, and the performance was evaluated by comparing the mean absolute error (MAE). All the models showed good results when the window size was 4 or 7 d, with the gated recurrent unit (GRU) performing well in all waters. The MAE results were within 0.161 m to 0.051 m for significant wave heights and 0.491 s to 0.272 s for periods. In addition, the GRU showed higher prediction accuracy for certain data with waves greater than 3 m or 8 s, which is likely due to the number of training parameters. When conducting marine and offshore research at new locations, the results presented in this study can help ensure safety and improve work efficiency. If additional wave-related data are obtained, more accurate wave predictions will be possible.